def test_step_table_join_mode_outer():
source = Resource("data/transform.csv")
target = transform(
source,
steps=[
steps.table_normalize(),
steps.table_join(
resource=Resource(
data=[["id", "note"], [1, "beer"], [4, "rum"]]),
field_name="id",
mode="outer",
),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "note",
"type": "string"
},
]
}
assert target.read_rows() == [
{
"id": 1,
"name": "germany",
"population": 83,
"note": "beer"
},
{
"id": 2,
"name": "france",
"population": 66,
"note": None
},
{
"id": 3,
"name": "spain",
"population": 47,
"note": None
},
{
"id": 4,
"name": None,
"population": None,
"note": "rum"
},
]
def test_step_table_join_mode_left_from_descriptor_issue_996():
source = Resource("data/transform.csv")
target = transform(
source,
steps=[
steps.table_normalize(),
steps.table_join(
{
"fieldName": "id",
"mode": "left"
},
resource=Resource(
data=[["id", "note"], [1, "beer"], [2, "vine"]]),
),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "note",
"type": "string"
},
]
}
assert target.read_rows() == [
{
"id": 1,
"name": "germany",
"population": 83,
"note": "beer"
},
{
"id": 2,
"name": "france",
"population": 66,
"note": "vine"
},
{
"id": 3,
"name": "spain",
"population": 47,
"note": None
},
]
def test_step_table_join_hash_is_true():
source = Resource("data/transform.csv")
target = transform(
source,
steps=[
steps.table_normalize(),
steps.table_join(
resource=Resource(
data=[["id", "note"], [1, "beer"], [2, "vine"]]),
field_name="id",
use_hash=True,
),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "note",
"type": "string"
},
]
}
assert target.read_rows() == [
{
"id": 1,
"name": "germany",
"population": 83,
"note": "beer"
},
{
"id": 2,
"name": "france",
"population": 66,
"note": "vine"
},
]
def test_step_table_join_with_name_is_not_first_field():
source = Resource(path="data/transform.csv")
target = transform(
source,
steps=[
steps.table_join(
resource=Resource(data=[["name", "note"], ["germany", "beer"],
["france", "vine"]]),
field_name="name",
),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
{
"name": "note",
"type": "string"
},
]
}
assert target.read_rows() == [
{
"id": 2,
"name": "france",
"population": 66,
"note": "vine"
},
{
"id": 1,
"name": "germany",
"population": 83,
"note": "beer"
},
]
def test_step_table_join_mode_anti():
source = Resource(path="data/transform.csv")
target = transform(
source,
steps=[
steps.table_normalize(),
steps.table_join(
resource=Resource(
data=[["id", "note"], [1, "beer"], [4, "rum"]]),
mode="anti",
),
],
)
assert target.schema == {
"fields": [
{
"name": "id",
"type": "integer"
},
{
"name": "name",
"type": "string"
},
{
"name": "population",
"type": "integer"
},
]
}
assert target.read_rows() == [
{
"id": 2,
"name": "france",
"population": 66
},
{
"id": 3,
"name": "spain",
"population": 47
},
]